Intelligent documentation for AI coding assistants.

Sensei solves the context pollution problem by orchestrating multiple knowledge sources and returning curated, accurate documentation with code examples.

Features

Multi-Source Documentation

Searches Context7, Tavily, and more to find the most relevant documentation for your query.

Intelligent Synthesis

Uses Claude to synthesize information from multiple sources into coherent, actionable answers.

MCP Server

Expose Sensei as an MCP tool for AI coding agents like Claude Code, Cursor, and Windsurf.

Self-Hostable

Run locally with SQLite or deploy with PostgreSQL. Your data, your infrastructure.

Quick Start

# Clone and install
git clone https://github.com/yourusername/sensei.git
cd sensei && uv sync

# Run Sensei
uv run sensei